Merge remote-tracking branch 'origin/develop' into contraction

6ef4e211 · Chao Liu · b0a2afb9 · 9e4429f9 · 6ef4e211 · 6ef4e211
Commit 6ef4e211 authored Jul 05, 2022 by Chao Liu
20 changed files
--- a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f64_f64_f64.cpp
+++ b/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_multiblock_atomic_add_f64_f64_f64.cpp
--- a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_b16_f32_b16.cpp
+++ b/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_b16_f32_b16.cpp
--- a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f16_f16_f16.cpp
+++ b/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f16_f16_f16.cpp
--- a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f16_f32_f16.cpp
+++ b/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f16_f32_f16.cpp
--- a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f32_f32.cpp
+++ b/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f32_f32.cpp
--- a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f64_f32.cpp
+++ b/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f32_f64_f32.cpp
--- a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f64_f64_f64.cpp
+++ b/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_f64_f64_f64.cpp
--- a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_i8_i32_i8.cpp
+++ b/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_i8_i32_i8.cpp
--- a/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_i8_i8_i8.cpp
+++ b/library/src/tensor_operation_instance/gpu/reduce/device_reduce_instance_threadwise_i8_i8_i8.cpp
--- a/profiler/CMakeLists.txt
+++ b/profiler/CMakeLists.txt
--- a/profiler/include/profile_batched_gemm_impl.hpp
+++ b/profiler/include/profile_batched_gemm_impl.hpp
--- a/profiler/include/profile_batched_gemm_reduce_impl.hpp
+++ b/profiler/include/profile_batched_gemm_reduce_impl.hpp
--- a/profiler/include/profile_conv_bwd_weight_impl.hpp
+++ b/profiler/include/profile_conv_bwd_weight_impl.hpp
--- a/profiler/include/profile_conv_fwd_bias_relu_add_impl.hpp
+++ b/profiler/include/profile_conv_fwd_bias_relu_add_impl.hpp
--- a/profiler/include/profile_conv_fwd_bias_relu_impl.hpp
+++ b/profiler/include/profile_conv_fwd_bias_relu_impl.hpp
--- a/profiler/include/profile_convnd_bwd_data_impl.hpp
+++ b/profiler/include/profile_convnd_bwd_data_impl.hpp
--- a/profiler/include/profile_convnd_fwd.hpp
+++ b/profiler/include/profile_convnd_fwd.hpp
--- a/profiler/include/profile_gemm_add_add_fastgelu_impl.hpp
+++ b/profiler/include/profile_gemm_add_add_fastgelu_impl.hpp
--- a/profiler/include/profile_gemm_bias_2d_impl.hpp
+++ b/profiler/include/profile_gemm_bias_2d_impl.hpp
--- a/profiler/include/profile_gemm_bias_add_reduce_impl.hpp
+++ b/profiler/include/profile_gemm_bias_add_reduce_impl.hpp